How investors measure risk

One of the most commonly used is standard deviation, a statistical measure of dispersion around a central tendency. You look at the average return of an investment and then finds it average standard deviation over the same time period.

Normal distributions ( the familiar bell shaped curve) dictate that the expected returns of the investment is likely to be one standard deviation from the average 67% of the time and two standard deviations from the average deviation 95% of the time. This helps investors evaluate risk numerically if they believe that they can tolerate the risk, financially and emotionally, they invest.

For example during a 15 year period from 1992 to 2007 the average annualized total return of the S&P500 was 10.7%. This number reveals what happened for the whole period but it does not say what happened along the way. The average standard deviation for that same period was 13,5%. This is the difference between the average return and the real return at most given points throughout that period.

When applying the bell curve model any given outcome should fall within one standard deviation of the mean about 67% of the time and within two standard deviations about 95% of the time. 

Thus an investor in the S&P 500 could expect the return at any given point during this period to be 10.7% plus or minus the standard deviation of 13.5% about 67% of the time, he may also assume a 27% ( two standard deviations) increase or decrease 95% of the time. If he can afford the loss, he invests.